Image Transformation Based on Generative Adversarial Networks
und
08. Okt. 2019
Über diesen Artikel
Online veröffentlicht: 08. Okt. 2019
Seitenbereich: 93 - 98
DOI: https://doi.org/10.21307/ijanmc-2019-053
Schlüsselwörter
© 2019 Chen Jie et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Figure 1.
Figure 2.
NETWORK STRUCTURE OF THE DISCRIMINATOR
| operation | Convolution kernel size | pace | Convolution kernel number | Batch normalization | activation function |
|---|---|---|---|---|---|
| convolution | 4×4 | 2 | 64 | No | Leaky Relu |
| convolution | 4×4 | 2 | 128 | Yes | Leaky Relu |
| convolution | 4×4 | 2 | 256 | Yes | Leaky Relu |
| convolution | 4×4 | 2 | 512 | Yes | Leaky Relu |
NETWORK STRUCTURE OF THE GENERATOR
| operation | Convolution kernel size | pace | Convolution kernel number | Batch normalization | activation function |
|---|---|---|---|---|---|
| convolution | 7×7 | 1 | 32 | No | Relu |
| convolution | 3×3 | 2 | 64 | Yes | Relu |
| convolution | 3×3 | 2 | 128 | Yes | Relu |
| convolution | 3×3 | 2 | 128 | Yes | Relu |
| convolution | 3×3 | 2 | 128 | Yes | Relu |
| convolution | 3×3 | 2 | 128 | Yes | Relu |
| convolution | 3×3 | 2 | 128 | Yes | Relu |
| convolution | 3×3 | 2 | 128 | Yes | Relu |
| deconvolution | 3×3 | 1/2 | 128 | Yes | Relu |
| deconvolution | 3×3 | 1/2 | 128 | Yes | Relu |
| deconvolution | 3×3 | 1/2 | 128 | Yes | Relu |
| deconvolution | 3×3 | 1/2 | 128 | Yes | Relu |
| deconvolution | 3×3 | 1/2 | 128 | Yes | Relu |
| deconvolution | 3×3 | 1/2 | 64 | Yes | Relu |
| deconvolution | 3×3 | 1/2 | 32 | Yes | Relu |
| deconvolution | 7×7 | 1 | 3 | Yes | Relu |